An improved feature selection method for classification on incomplete data: Non-negative latent factor-incorporated duplicate MIC

作者：

Highlights：

• A three-step method is proposed for dimensionality reduction of incomplete data.

• The initial feature selection improves the effectiveness of imputation.

• The improved maximal information coefficient effectively reduces redundancy.

• The combination of two filters achieves less computation and higher accuracy.

摘要

•A three-step method is proposed for dimensionality reduction of incomplete data.•The initial feature selection improves the effectiveness of imputation.•The improved maximal information coefficient effectively reduces redundancy.•The combination of two filters achieves less computation and higher accuracy.

论文关键词：Feature selection,Incomplete data,Non-negative latent factor,Duplicate maximal information coefficient,Low-redundancy

论文评审过程：Received 13 April 2021, Revised 23 June 2022, Accepted 20 August 2022, Available online 28 August 2022, Version of Record 7 September 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118654